youtubescraper 0.0.7
Sign up to get free protection for your applications and to get access to all the features.
- data/CHANGELOG +20 -0
- data/MIT-LICENSE +20 -0
- data/README +23 -0
- data/lib/youtube/browsescraper.rb +260 -0
- data/lib/youtube/searchresultscraper.rb +263 -0
- data/lib/youtube/searchresultscraper.rb~ +263 -0
- data/lib/youtube/video.rb +62 -0
- data/test/html/dataN_noMsgN.htm +387 -0
- data/test/html/dataY_noMsgY.htm +1507 -0
- data/test/html/scraping_error.html +1503 -0
- data/test/youtube_scraper_test.rb +89 -0
- data/test/youtube_scraper_test.rb~ +92 -0
- metadata +69 -0
data/CHANGELOG
ADDED
@@ -0,0 +1,20 @@
|
|
1
|
+
0.0.1 2006-11-26
|
2
|
+
First public release
|
3
|
+
|
4
|
+
0.0.2 2006-12-03
|
5
|
+
Add rdoc.
|
6
|
+
Add each() method into YouTube::SearchResultScraper
|
7
|
+
|
8
|
+
0.0.3 2006-12-22
|
9
|
+
Add error check.
|
10
|
+
Add attribute for video_count, video_from, video_to
|
11
|
+
|
12
|
+
0.0.4 2007-02-01
|
13
|
+
Add error check for scraping of pagination.
|
14
|
+
Fix scraping rule for html markup change of youtube.
|
15
|
+
|
16
|
+
0.0.5 2007-02-16
|
17
|
+
Fix scraping rule for video_count, video_from, video_to
|
18
|
+
|
19
|
+
0.0.6 2007-02-16
|
20
|
+
Fix error handling for video_count, video_from, video_to
|
data/MIT-LICENSE
ADDED
@@ -0,0 +1,20 @@
|
|
1
|
+
Copyright (C) 2006 by in3c.org
|
2
|
+
|
3
|
+
Permission is hereby granted, free of charge, to any person obtaining
|
4
|
+
a copy of this software and associated documentation files (the
|
5
|
+
"Software"), to deal in the Software without restriction, including
|
6
|
+
without limitation the rights to use, copy, modify, merge, publish,
|
7
|
+
distribute, sublicense, and/or sell copies of the Software, and to
|
8
|
+
permit persons to whom the Software is furnished to do so, subject to
|
9
|
+
the following conditions:
|
10
|
+
|
11
|
+
The above copyright notice and this permission notice shall be
|
12
|
+
included in all copies or substantial portions of the Software.
|
13
|
+
|
14
|
+
THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
|
15
|
+
EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
|
16
|
+
MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND
|
17
|
+
NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS BE
|
18
|
+
LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN ACTION
|
19
|
+
OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN CONNECTION
|
20
|
+
WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE SOFTWARE.
|
data/README
ADDED
@@ -0,0 +1,23 @@
|
|
1
|
+
Introduction
|
2
|
+
|
3
|
+
Youtube::SearchResultScraper scrapes video information from search result page on www.youtube.com.
|
4
|
+
You can get result as array or xml.
|
5
|
+
XML format is same as YouTube Developer API (www.youtube.com/dev_api_ref?m=youtube.videos.list_by_tag).
|
6
|
+
|
7
|
+
Example
|
8
|
+
|
9
|
+
require "rubygems"
|
10
|
+
require "youtube/searchresultscraper"
|
11
|
+
|
12
|
+
scraper = Youtube::SearchResultScraper.new(keyword, page)
|
13
|
+
scraper.open
|
14
|
+
scraper.scrape
|
15
|
+
puts scraper.get_xml
|
16
|
+
|
17
|
+
More Information
|
18
|
+
|
19
|
+
http://www.ark-web.jp/sandbox/wiki/184.html (japanese only)
|
20
|
+
|
21
|
+
Author: Yuki SHIDA, shida@in3c.org
|
22
|
+
Version: 0.0.2
|
23
|
+
License: MIT license
|
@@ -0,0 +1,260 @@
|
|
1
|
+
#--
|
2
|
+
# Copyright (C) 2006 by in3c.org, ARK-Web co., ltd
|
3
|
+
#
|
4
|
+
# Permission is hereby granted, free of charge, to any person obtaining
|
5
|
+
# a copy of this software and associated documentation files (the
|
6
|
+
# "Software"), to deal in the Software without restriction, including
|
7
|
+
# without limitation the rights to use, copy, modify, merge, publish,
|
8
|
+
# distribute, sublicense, and/or sell copies of the Software, and to
|
9
|
+
# permit persons to whom the Software is furnished to do so, subject to
|
10
|
+
# the following conditions:
|
11
|
+
#
|
12
|
+
# The above copyright notice and this permission notice shall be
|
13
|
+
# included in all copies or substantial portions of the Software.
|
14
|
+
#
|
15
|
+
# THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
|
16
|
+
# EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
|
17
|
+
# MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND
|
18
|
+
# NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS BE
|
19
|
+
# LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN ACTION
|
20
|
+
# OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN CONNECTION
|
21
|
+
# WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE SOFTWARE.
|
22
|
+
#++
|
23
|
+
# :main:Youtube::BrowseScraper
|
24
|
+
# :title:Youtube::BrowseScraper RDoc Documentation
|
25
|
+
|
26
|
+
require 'open-uri'
|
27
|
+
require 'cgi'
|
28
|
+
require 'rubygems'
|
29
|
+
require 'hpricot'
|
30
|
+
require 'video'
|
31
|
+
|
32
|
+
module Youtube #:nodoc:
|
33
|
+
# = Introduction
|
34
|
+
# Youtube::BrowseScraper scrapes video information from search result page
|
35
|
+
# on http://www.youtube.com.
|
36
|
+
#
|
37
|
+
# You can get result as array or xml.
|
38
|
+
#
|
39
|
+
# XML format is same as YouTube Developer API
|
40
|
+
# (http://www.youtube.com/dev_api_ref?m=youtube.videos.list_by_tag).
|
41
|
+
#
|
42
|
+
# = Example
|
43
|
+
# require "rubygems"
|
44
|
+
# require "youtube/BrowseScraper"
|
45
|
+
#
|
46
|
+
# scraper = Youtube::BrowseScraper.new(browse, time, category, language, page)
|
47
|
+
# scraper.open
|
48
|
+
# data = scraper.scrape
|
49
|
+
# p data
|
50
|
+
#
|
51
|
+
# = More Information
|
52
|
+
#
|
53
|
+
#
|
54
|
+
# Author:: Syuichi Kohata <sgkohata@gmail.com>
|
55
|
+
# Version:: 0.0.1
|
56
|
+
# License:: MIT license
|
57
|
+
|
58
|
+
class BrowseScraper
|
59
|
+
# constants for browse parameter(default MoseRecent)
|
60
|
+
MostRecent = 'mr'
|
61
|
+
MostViewed = 'mp'
|
62
|
+
TopRated = 'tr'
|
63
|
+
MostDiscussed = 'md'
|
64
|
+
TopFavorites = 'mf'
|
65
|
+
MostLinked = 'mrd'
|
66
|
+
RecentryFeatured = 'rf'
|
67
|
+
MostResponded = 'ms'
|
68
|
+
WatchOnMobile = 'mv'
|
69
|
+
BrowseArray = [MostRecent,
|
70
|
+
MostViewed,
|
71
|
+
TopRated,
|
72
|
+
MostDiscussed,
|
73
|
+
TopFavorites,
|
74
|
+
MostLinked,
|
75
|
+
RecentryFeatured,
|
76
|
+
MostResponded,
|
77
|
+
WatchOnMobile]
|
78
|
+
|
79
|
+
# constants for time parameter(default Today)
|
80
|
+
Today = 't'
|
81
|
+
ThisWeek = 'w'
|
82
|
+
ThisMonth = 'm'
|
83
|
+
All = 'a'
|
84
|
+
TimeArray = [Today,
|
85
|
+
ThisWeek,
|
86
|
+
ThisMonth,
|
87
|
+
All]
|
88
|
+
|
89
|
+
# constants for category parameter(default 0)
|
90
|
+
AllCategory = 0
|
91
|
+
AutosVehicles = 2
|
92
|
+
Comedy = 23
|
93
|
+
Entertainment = 24
|
94
|
+
FilmAnimation = 1
|
95
|
+
GadgetsGames = 20
|
96
|
+
HowtoDIY = 26
|
97
|
+
Music = 10
|
98
|
+
NewsPolitics = 25
|
99
|
+
PeopleBlogs = 22
|
100
|
+
PetsAnimals = 15
|
101
|
+
Sports = 17
|
102
|
+
TravelPlaces = 19
|
103
|
+
|
104
|
+
# constants for language parameter(default '')
|
105
|
+
AllLanguage = ''
|
106
|
+
English = 'EN'
|
107
|
+
Spanish = 'ES'
|
108
|
+
Japanese = 'JP'
|
109
|
+
German = 'DE'
|
110
|
+
Chinese = 'CN'
|
111
|
+
French = 'FR'
|
112
|
+
LanguageArray = [AllLanguage,
|
113
|
+
English,
|
114
|
+
Spanish,
|
115
|
+
Japanese,
|
116
|
+
German,
|
117
|
+
Chinese,
|
118
|
+
French]
|
119
|
+
|
120
|
+
attr_accessor :browse
|
121
|
+
attr_accessor :time
|
122
|
+
attr_accessor :category
|
123
|
+
attr_accessor :language
|
124
|
+
attr_accessor :page
|
125
|
+
attr_reader :video_count
|
126
|
+
attr_reader :video_from
|
127
|
+
attr_reader :video_to
|
128
|
+
|
129
|
+
@@youtube_search_base_url = 'http://www.youtube.com/browse'
|
130
|
+
|
131
|
+
# Create Youtube::BrowseScraper object
|
132
|
+
# (default parameter )
|
133
|
+
#
|
134
|
+
# You cannot specify number of videos per page.
|
135
|
+
# Always, the number of videos is 20 per page.
|
136
|
+
def initialize browse = MostRecent, time = Today, category = AllCategory, language = AllLanguage, page = 1
|
137
|
+
@browse = browse
|
138
|
+
@time = time
|
139
|
+
@category = category
|
140
|
+
@language = language
|
141
|
+
@page = page
|
142
|
+
|
143
|
+
errors = []
|
144
|
+
errors << "browse" if BrowseArray.index(@browse) == nil
|
145
|
+
errors << "time" if TimeArray.index(@time) == nil
|
146
|
+
errors << "language" if LanguageArray.index(@language) == nil
|
147
|
+
unless errors.empty? then
|
148
|
+
error_msg = "parameter error occurred.\n"
|
149
|
+
errors.each do |error|
|
150
|
+
error_msg << error + " is invalid.\n"
|
151
|
+
end
|
152
|
+
raise error_msg
|
153
|
+
end
|
154
|
+
end
|
155
|
+
|
156
|
+
# Get search result from youtube by specified keyword.
|
157
|
+
def open
|
158
|
+
@url = @@youtube_search_base_url
|
159
|
+
@url += "?s=#{@browse}"
|
160
|
+
@url += "&t=#{@time}"
|
161
|
+
@url += "&c=#{@category}"
|
162
|
+
@url += "&l=#{@language}"
|
163
|
+
@url += "&p=#{@page}"
|
164
|
+
@html = Kernel.open(@url).read
|
165
|
+
@search_result = Hpricot.parse(@html)
|
166
|
+
end
|
167
|
+
|
168
|
+
# Scrape video information from search result html.
|
169
|
+
def scrape
|
170
|
+
@videos = []
|
171
|
+
@video_count = 0
|
172
|
+
@search_result.search('//div[@class="v120vEntry"]').each do |video_html|
|
173
|
+
video = Youtube::Video.new
|
174
|
+
|
175
|
+
video.id = scrape_id(video_html)
|
176
|
+
video.author = scrape_author(video_html)
|
177
|
+
video.title = scrape_title(video_html)
|
178
|
+
video.length_seconds = scrape_length_seconds(video_html)
|
179
|
+
video.rating_avg = scrape_rating_avg(video_html)
|
180
|
+
video.view_count = scrape_view_count(video_html)
|
181
|
+
video.thumbnail_url = scrape_thumbnail_url(video_html)
|
182
|
+
|
183
|
+
check_video video
|
184
|
+
|
185
|
+
@videos << video
|
186
|
+
@video_count += 1
|
187
|
+
end
|
188
|
+
@videos
|
189
|
+
end
|
190
|
+
|
191
|
+
# Return videos information as XML Format.
|
192
|
+
def get_xml
|
193
|
+
end
|
194
|
+
|
195
|
+
def replace_document_write_javascript
|
196
|
+
@html.gsub!(%r{<script language="javascript" type="text/javascript">.*?document.write\('(.*?)'\).*?</script>}m, '\1')
|
197
|
+
end
|
198
|
+
|
199
|
+
def scrape_id video_html
|
200
|
+
scrape_thumbnail_url(video_html).sub(%r{.*/([^/]+)/[^/]+.jpg}, '\1')
|
201
|
+
end
|
202
|
+
|
203
|
+
def scrape_thumbnail_url video_html
|
204
|
+
video_html.search("img[@class='vimg120']").to_html.sub(/.*src="(.*?)".*/, '\1')
|
205
|
+
end
|
206
|
+
|
207
|
+
def scrape_title video_html
|
208
|
+
video_html.search('div[@class="vtitle"]/a').inner_html
|
209
|
+
end
|
210
|
+
|
211
|
+
def scrape_length_seconds video_html
|
212
|
+
length_seconds = video_html.search("span[@class='runtime']").inner_html
|
213
|
+
length_seconds =~ /(\d\d):(\d\d)/
|
214
|
+
$1.to_i * 60 + $2.to_i
|
215
|
+
end
|
216
|
+
|
217
|
+
def scrape_rating_avg video_html
|
218
|
+
video_html.search("img[@src='/img/icn_star_full_11x11.gif']").size +
|
219
|
+
video_html.search("img[@src='/img/icn_star_half_11x11.gif']").size * 0.5
|
220
|
+
end
|
221
|
+
|
222
|
+
def scrape_thumbnail_url video_html
|
223
|
+
video_html.search("img[@class=' vimg ']").to_html.sub(/.*src="(.*?)".*/, '\1')
|
224
|
+
end
|
225
|
+
|
226
|
+
def scrape_author video_html
|
227
|
+
video_html.search("div[@class='vfacets']").inner_html.sub(/.*From:<\/span> <a.*?>(.*?)<\/a>.*/m, '\1')
|
228
|
+
end
|
229
|
+
|
230
|
+
def scrape_view_count video_html
|
231
|
+
@num = video_html.search("div[@class='vfacets']").inner_html.sub(/.*Views:<\/span> ([\d,]+).*/m, '\1')
|
232
|
+
@num.gsub(/,/, '').to_i
|
233
|
+
end
|
234
|
+
|
235
|
+
def check_video video
|
236
|
+
errors = []
|
237
|
+
|
238
|
+
errors << "id" if video.id.empty?
|
239
|
+
errors << "author" if video.author.empty?
|
240
|
+
errors << "title" if video.title.empty?
|
241
|
+
errors << "length_seconds" if video.length_seconds.to_s.empty?
|
242
|
+
errors << "thumbnail_url" if video.thumbnail_url.empty?
|
243
|
+
|
244
|
+
unless errors.empty? then
|
245
|
+
error_msg = "scraping error occurred.\n"
|
246
|
+
errors.each do |error|
|
247
|
+
error_msg << error + " is not setted.\n"
|
248
|
+
end
|
249
|
+
raise error_msg
|
250
|
+
end
|
251
|
+
end
|
252
|
+
|
253
|
+
def each
|
254
|
+
@videos.each do |video|
|
255
|
+
yield video
|
256
|
+
end
|
257
|
+
end
|
258
|
+
|
259
|
+
end
|
260
|
+
end
|
@@ -0,0 +1,263 @@
|
|
1
|
+
#--
|
2
|
+
# Copyright (C) 2006 by in3c.org, ARK-Web co., ltd
|
3
|
+
#
|
4
|
+
# Permission is hereby granted, free of charge, to any person obtaining
|
5
|
+
# a copy of this software and associated documentation files (the
|
6
|
+
# "Software"), to deal in the Software without restriction, including
|
7
|
+
# without limitation the rights to use, copy, modify, merge, publish,
|
8
|
+
# distribute, sublicense, and/or sell copies of the Software, and to
|
9
|
+
# permit persons to whom the Software is furnished to do so, subject to
|
10
|
+
# the following conditions:
|
11
|
+
#
|
12
|
+
# The above copyright notice and this permission notice shall be
|
13
|
+
# included in all copies or substantial portions of the Software.
|
14
|
+
#
|
15
|
+
# THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
|
16
|
+
# EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
|
17
|
+
# MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND
|
18
|
+
# NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS BE
|
19
|
+
# LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN ACTION
|
20
|
+
# OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN CONNECTION
|
21
|
+
# WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE SOFTWARE.
|
22
|
+
#++
|
23
|
+
# :main:Youtube::SearchResultScraper
|
24
|
+
# :title:Youtube::SearchResultScraper RDoc Documentation
|
25
|
+
|
26
|
+
require 'open-uri'
|
27
|
+
require 'cgi'
|
28
|
+
require 'rubygems'
|
29
|
+
require 'hpricot'
|
30
|
+
require 'youtube/video'
|
31
|
+
|
32
|
+
module Youtube #:nodoc:
|
33
|
+
|
34
|
+
# = Introduction
|
35
|
+
# Youtube::SearchResultScraper scrapes video information from search result page
|
36
|
+
# on http://www.youtube.com.
|
37
|
+
#
|
38
|
+
# You can get result as array or xml.
|
39
|
+
#
|
40
|
+
# XML format is same as YouTube Developer API
|
41
|
+
# (http://www.youtube.com/dev_api_ref?m=youtube.videos.list_by_tag).
|
42
|
+
#
|
43
|
+
# = Example
|
44
|
+
# require "rubygems"
|
45
|
+
# require "youtube/searchresultscraper"
|
46
|
+
#
|
47
|
+
# scraper = Youtube::SearchResultScraper.new(keyword, page)
|
48
|
+
# scraper.open
|
49
|
+
# scraper.scrape
|
50
|
+
# puts scraper.get_xml
|
51
|
+
#
|
52
|
+
# = More Information
|
53
|
+
# http://www.ark-web.jp/sandbox/wiki/184.html (japanese only)
|
54
|
+
#
|
55
|
+
# Author:: Yuki SHIDA <shida@in3c.org>
|
56
|
+
# Author:: Konuma Akio <konuma@ark-web.jp>
|
57
|
+
# Version:: 0.0.3
|
58
|
+
# License:: MIT license
|
59
|
+
|
60
|
+
class SearchResultScraper
|
61
|
+
|
62
|
+
attr_accessor :keyword
|
63
|
+
attr_accessor :page
|
64
|
+
attr_reader :video_count
|
65
|
+
attr_reader :video_from
|
66
|
+
attr_reader :video_to
|
67
|
+
|
68
|
+
@@youtube_search_base_url = "http://www.youtube.com/results?search_query="
|
69
|
+
|
70
|
+
# Create Youtube::SearchResultScraper object specifying keyword and number of page.
|
71
|
+
#
|
72
|
+
# You cannot specify number of videos per page.
|
73
|
+
# Always, the number of videos is 20 per page.
|
74
|
+
#
|
75
|
+
# * keyword - specify keyword that you want to search on YouTube.
|
76
|
+
# You must specify keyword encoded by UTF-8.
|
77
|
+
# * page - specify number of page
|
78
|
+
|
79
|
+
def initialize keyword, page=nil
|
80
|
+
@keyword = keyword
|
81
|
+
@page = page if not page == nil
|
82
|
+
end
|
83
|
+
|
84
|
+
# Get search result from youtube by specified keyword.
|
85
|
+
def open
|
86
|
+
@url = @@youtube_search_base_url + CGI.escape(@keyword)
|
87
|
+
@url += "&page=#{@page}" if not @page == nil
|
88
|
+
@html = Kernel.open(@url).read
|
89
|
+
replace_document_write_javascript
|
90
|
+
@search_result = Hpricot.parse(@html)
|
91
|
+
end
|
92
|
+
|
93
|
+
# Scrape video information from search result html.
|
94
|
+
def scrape
|
95
|
+
@videos = []
|
96
|
+
|
97
|
+
@search_result.search("//div[@class='vEntry']").each do |video_html|
|
98
|
+
video = Youtube::Video.new
|
99
|
+
video.id = scrape_id(video_html)
|
100
|
+
video.author = scrape_author(video_html)
|
101
|
+
video.title = scrape_title(video_html)
|
102
|
+
video.length_seconds = scrape_length_seconds(video_html)
|
103
|
+
video.rating_avg = scrape_rating_avg(video_html)
|
104
|
+
video.rating_count = scrape_rating_count(video_html)
|
105
|
+
video.description = scrape_description(video_html)
|
106
|
+
video.view_count = scrape_view_count(video_html)
|
107
|
+
video.thumbnail_url = scrape_thumbnail_url(video_html)
|
108
|
+
video.tags = scrape_tags(video_html)
|
109
|
+
video.url = scrape_url(video_html)
|
110
|
+
|
111
|
+
check_video video
|
112
|
+
|
113
|
+
@videos << video
|
114
|
+
end
|
115
|
+
|
116
|
+
@video_count = scrape_video_count
|
117
|
+
@video_from = scrape_video_from
|
118
|
+
@video_to = scrape_video_to
|
119
|
+
|
120
|
+
raise "scraping error" if (is_no_result != @videos.empty?)
|
121
|
+
|
122
|
+
@videos
|
123
|
+
end
|
124
|
+
|
125
|
+
# Iterator for scraped videos.
|
126
|
+
def each
|
127
|
+
@videos.each do |video|
|
128
|
+
yield video
|
129
|
+
end
|
130
|
+
end
|
131
|
+
|
132
|
+
# Return videos information as XML Format.
|
133
|
+
def get_xml
|
134
|
+
xml = "<ut_response status=\"ok\">" +
|
135
|
+
"<video_count>" + @video_count.to_s + "</video_count>" +
|
136
|
+
"<video_list>\n"
|
137
|
+
each do |video|
|
138
|
+
xml += video.to_xml
|
139
|
+
end
|
140
|
+
xml += "</video_list></ut_response>"
|
141
|
+
end
|
142
|
+
|
143
|
+
private
|
144
|
+
|
145
|
+
def replace_document_write_javascript
|
146
|
+
@html.gsub!(%r{<script language="javascript" type="text/javascript">.*?document.write\('(.*?)'\).*?</script>}m, '\1')
|
147
|
+
end
|
148
|
+
|
149
|
+
def scrape_id video_html
|
150
|
+
scrape_thumbnail_url(video_html).sub(%r{.*/([^/]+)/[^/]+.jpg}, '\1')
|
151
|
+
end
|
152
|
+
|
153
|
+
def scrape_author video_html
|
154
|
+
video_html.search("div[@class='vfacets']").inner_html.sub(/.*From:<\/span> <a.*?>(.*?)<\/a>.*/m, '\1')
|
155
|
+
end
|
156
|
+
|
157
|
+
def scrape_title video_html
|
158
|
+
video_html.search("div[@class='vtitle']/a").inner_html
|
159
|
+
end
|
160
|
+
|
161
|
+
def scrape_length_seconds video_html
|
162
|
+
length_seconds = video_html.search("span[@class='runtime']").inner_html
|
163
|
+
length_seconds =~ /(\d\d):(\d\d)/
|
164
|
+
$1.to_i * 60 + $2.to_i
|
165
|
+
end
|
166
|
+
|
167
|
+
def scrape_rating_avg video_html
|
168
|
+
video_html.search("img[@src='/img/star_sm.gif']").size +
|
169
|
+
video_html.search("img[@src='/img/star_sm_half.gif']").size * 0.5
|
170
|
+
end
|
171
|
+
|
172
|
+
def scrape_rating_count video_html
|
173
|
+
video_html.search("div[@class='rating']").inner_html.sub(/(\d+) rating/, '\1').to_i
|
174
|
+
end
|
175
|
+
|
176
|
+
def scrape_description video_html
|
177
|
+
description = video_html.search("div[@class='vdesc']/span").inner_html.sub(/^\n\t(.*?)\n\t$/m, '\1')
|
178
|
+
end
|
179
|
+
|
180
|
+
def scrape_view_count video_html
|
181
|
+
video_html.search("div[@class='vfacets']").inner_html.sub(/.*Views:<\/span> (\d+).*/m, '\1').to_i
|
182
|
+
end
|
183
|
+
|
184
|
+
def scrape_tags video_html
|
185
|
+
tags = []
|
186
|
+
video_html.search("div[@class='vtagValue']/a").each do |tag|
|
187
|
+
tags << tag.inner_html
|
188
|
+
end
|
189
|
+
tags.join(" ")
|
190
|
+
end
|
191
|
+
|
192
|
+
def scrape_thumbnail_url video_html
|
193
|
+
video_html.search("img[@class='vimg120']").to_html.sub(/.*src="(.*?)".*/, '\1')
|
194
|
+
end
|
195
|
+
|
196
|
+
def scrape_url video_html
|
197
|
+
"http://www.youtube.com" +
|
198
|
+
video_html.search("div[@class='vtitle']/a").to_html.sub(/.*href="(.*?)".*/m, '\1')
|
199
|
+
end
|
200
|
+
|
201
|
+
def scrape_result_header
|
202
|
+
@search_result.search("div[@id='sectionHeader']").inner_html
|
203
|
+
end
|
204
|
+
|
205
|
+
def scrape_video_count
|
206
|
+
video_count = scrape_result_header
|
207
|
+
unless video_count.sub!(/.+Results \d+-\d+ of\s*(|about )([0-9,]+)/m , '\2')
|
208
|
+
raise "no video count: " + @url unless is_no_result
|
209
|
+
end
|
210
|
+
video_count.gsub!(/,/, '')
|
211
|
+
video_count.to_i
|
212
|
+
end
|
213
|
+
|
214
|
+
def scrape_video_from
|
215
|
+
video_from = scrape_result_header
|
216
|
+
unless video_from.sub!(/.+Results (\d+)/m, '\1')
|
217
|
+
raise "no video from: " + @url unless is_no_result
|
218
|
+
end
|
219
|
+
video_from.to_i
|
220
|
+
end
|
221
|
+
|
222
|
+
def scrape_video_to
|
223
|
+
video_to = scrape_result_header
|
224
|
+
unless video_to.sub!(/.+Results \d+-(\d+)/m, '\1')
|
225
|
+
raise "no video to: " + @url unless is_no_result
|
226
|
+
end
|
227
|
+
video_to.to_i
|
228
|
+
end
|
229
|
+
|
230
|
+
def is_no_result
|
231
|
+
if @is_no_result == nil
|
232
|
+
@is_no_result = @html.include?('No Videos found')
|
233
|
+
end
|
234
|
+
@is_no_result
|
235
|
+
end
|
236
|
+
|
237
|
+
def check_video video
|
238
|
+
errors = []
|
239
|
+
|
240
|
+
errors << "author" if video.author.empty?
|
241
|
+
errors << "id" if video.id.empty?
|
242
|
+
errors << "title" if video.title.empty?
|
243
|
+
errors << "length_seconds" if video.length_seconds.to_s.empty?
|
244
|
+
errors << "rating_avg" if video.rating_avg.to_s.empty?
|
245
|
+
errors << "rating_count" if video.rating_count.to_s.empty?
|
246
|
+
errors << "description" if video.description.empty?
|
247
|
+
errors << "view_count" if video.view_count.to_s.empty?
|
248
|
+
errors << "tags" if video.tags.empty?
|
249
|
+
errors << "url" if video.url.empty?
|
250
|
+
errors << "thumbnail_url" if video.thumbnail_url.empty?
|
251
|
+
|
252
|
+
unless errors.empty? then
|
253
|
+
error_msg = "scraping error occurred.\n"
|
254
|
+
errors.each do |error|
|
255
|
+
error_msg << error + " is not setted.\n"
|
256
|
+
end
|
257
|
+
raise error_msg
|
258
|
+
end
|
259
|
+
end
|
260
|
+
|
261
|
+
end
|
262
|
+
|
263
|
+
end
|